Machine Learning Research
Better Video, Fewer Tokens: STORM Processes Fewer Tokens And Still Beats GPT-4o On Video Understanding Benchmarks
Researchers reduced the number of tokens needed to represent video frames to be fed to a transformer.
Transformers
Machine Learning Research
Memory Layers for More-Factual Output: Meta researchers build Llama-style models that recall details without needing more computing resources
Improving a large language model’s factual accuracy typically requires making it bigger, which in turn, involves more computation. Researchers devised an architecture that enables models to recall relevant details without significantly increasing the amount of computation required.
Machine Learning Research
Inferring Customer Preferences: LLMs boost shopping recommendations by decoding what users want
Large language models can improve systems that recommend items to purchase by inferring customer preferences.
Machine Learning Research
Toward LLMs That Understand Misspellings: New byte-based model beats Llama 3 on spelling, noise, and translation
Researchers built a model that’s more robust to noisy inputs like misspellings, smarter about character-level information like the number of R's in strawberry, and potentially better able to understand unfamiliar languages that might share groups of letters with familiar languages.
Machine Learning Research
Better Than Trees for Tabular Data: Transformers can outperform decision trees at predicting unlabeled spreadsheet cells
If you have a collection of variables that represent, say, a cancer patient and you want to classify the patient’s illness as likely cancer or not, algorithms based on decision trees, such as gradient-boosted trees, typically perform better than neural networks.
Machine Learning Research
Reasoning in Vectors, Not Text: Meta introduces Chain of Continuous Thought (Coconut) to improve next-token prediction
Although large language models can improve their performance by generating a chain of thought (CoT) — intermediate text tokens that break down the process of responding to a prompt into a series of steps.
Machine Learning Research
Calibrating Contrast: X-CLR, an approach to contrastive learning for better vision models
Contrastive loss functions make it possible to produce good embeddings without labeled data. A twist on this idea makes even more useful embeddings.
Machine Learning Research
Multimodal Modeling on the Double: Google introduces Gemini 2.0 Flash, a faster, more capable AI model
Google’s Gemini 2.0 Flash, the first member of its updated Gemini family of large multimodal models, combines speed with performance that exceeds that of its earlier flagship model, Gemini 1.5 Pro, on several measures.
Hardware
Object Detection for Small Devices: Grounding DINO 1.5, an edge device model built for faster, smarter object detection
An open source model is designed to perform sophisticated object detection on edge devices like phones, cars, medical equipment, and smart doorbells.
Machine Learning Research
More-Efficient Training for Transformers: Researchers reduce transformer training costs by 20% with minimal performance loss
Researchers cut the processing required to train transformers by around 20 percent with only a slight degradation in performance.
Machine Learning Research
Making LLMs Explainable: Google’s Gemma Scope probes how large language models think
Researchers have probed the inner workings of individual layers of large language models. A new tool applies this approach to all layers.
Machine Learning Research
Long Context Gets Up to Speed: AI21 Labs’ Jamba 1.5 outpaces transformers in long-text processing
A new model generates tokens faster than current transformers, especially when processing long inputs.